A Model Context Protocol server implementation for ChatterBox, enabling AI agents to interact with online meetings and generate meeting summaries.

The ChatterBox MCP Server provides tools for AI agents to:

• Join online meetings (Zoom, Google Meet, or Microsoft Teams)
• Capture transcripts and recordings
• Generate meeting summaries

To install chatterboxio-mcp-server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @OverQuotaAI/chatterboxio-mcp-server --client claude

You can install the dependencies using either npm or pnpm:

# Using npm
npm install

# Using pnpm
pnpm install

You can get your API keys for free by registering on our website at ChatterBox. After registration, you'll receive your API endpoint and key.

Create a .env file in the root directory with the following variables:

CHATTERBOX_API_ENDPOINT=https://api.chatter-box.io
CHATTERBOX_API_KEY=your_api_key_here

pnpm start

Join a Zoom or Google Meet meeting and capture transcript and audio recording.

Parameters:

• platform (string): The online conference platform ("zoom", "googlemeet", or "teams")
• meetingId (string): The ID of the meeting
• meetingPassword (string, optional): The password or the passcode for the meeting
• botName (string): The name of the bot
• webhookUrl (string, optional): URL to receive webhook events for meeting status

Get information about a meeting, including transcript and recording.

Parameters:

• sessionId (string): The session ID to get information for

Generate a concise summary of a meeting's contents from its transcript.

Parameters:

• transcript (string): The meeting transcript to summarize

• Node.js 16+
• npm or yarn

pnpm run build

To debug the MCP server using the MCP Inspector:

npx @modelcontextprotocol/inspector

This project is licensed under the MIT License - see the LICENSE file for details.

For support, please visit ChatterBox Documentation or contact support@chatter-box.io.

Contributions are welcome! Please feel free to submit a Pull Request.